Wen Wu

Dr. Wen Wu

orcid

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 October 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JYJiaqi Yin
Jiaqi Yin
YZYi Zhu
Yi Zhu
TGTiong-Thye Goh
Tiong-Thye Goh
WWWen Wu
Wen Wu
YHYi Hu
Yi Hu
Educational chatbots (ECs) can offer instructional feedback to enhance learning. However, the effect of metacognitive feedback on science education has not been fully explored. This study focuses on the effect of the EC with metacognitive feedback on students’ knowledge retention, transfer, and intrinsic motivation in the field of biology science. A between-group experimental design with 62 college students was conducted. Students in the experiment group received metacognitive feedback, whereas students in the control group received no feedback. The results of the ANCOVA test showed that students in the experiment group demonstrated better knowledge retention and transfer than those in the control group (F = 13.11, p = 0.001; F = 14.39, p < 0.001). Further, students in the experiment group reported more learning interest and higher perceived competence and value than those in the control group (F = 3.72, p = 0.001; F = 1.91, p = 0.009; F = 2.70, p = 0.004). In addition, correlation analysis revealed that perceived competence in the metacognitive feedback group was positively related to knowledge transfer (r = 0.39, p = 0.032). However, there was no significant difference in perceived pressure between both groups (p = 0.203). This study highlights the potential of the EC with metacognitive feedback for science learning.

14 June 2022 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
JCJiayi Chen
Jiayi Chen
WWWen Wu
Wen Wu
LSLiye Shi
Liye Shi
WZWei Zheng
Wei Zheng
Liang HeLiang He
Liang He

6 January 2022 in Information Sciences
Verified
Journal Article
Closed access
LSLiye Shi
Liye Shi
WWWen Wu
Wen Wu
WGWang Guo
Wang Guo
WHWenxin Hu
Wenxin Hu
JCJiayi Chen
Jiayi Chen
LHLiang He
Liang He

10 February 2022 in Knowledge-Based Systems
Verified
Journal Article
Closed access
LSLiye Shi
Liye Shi
WWWen Wu
Wen Wu
WHWenxin Hu
Wenxin Hu
JZJie Zhou
Jie Zhou
JCJiayi Chen
Jiayi Chen
LHLiang He
Liang He

19 November 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JCJiayi Chen
Jiayi Chen
WWWen Wu
Wen Wu
LSLiye Shi
Liye Shi
Yu JiYu Ji
Yu Ji
WHWenxin Hu
Wenxin Hu
Liang HeLiang He
Liang He
Sequential recommendations have made great strides in accurately predicting the future behavior of users. However, seeking accuracy alone may bring side effects such as unfair and overspecialized recommendation results. In this work, we focus on the calibrated recommendations for sequential recommendation, which is connected to both fairness and diversity. On the one hand, it aims to provide fairer recommendations whose preference distributions are consistent with users’ historical behaviors. On the other hand, it can improve the diversity of recommendations to a certain degree. But existing methods for calibration have mainly relied on the post-processing on the candidate lists, which require more computation time in generating recommendations. In addition, they fail to establish the relationship between accuracy and calibration, leading to the limitation of accuracy. To handle these problems, we propose an end-to-end framework to provide both accurate and calibrated recommendations for sequential recommendation. We design an objective function to calibrate the interests between recommendation lists and historical behaviors. We also provide distribution modification approaches to improve the diversity and mitigate the effect of imbalanced interests. In addition, we design a decoupled-aggregated model to improve the recommendation. The framework assigns two objectives to two individual sequence encoders, and aggregates the outputs by extracting useful information. Experiments on benchmark datasets validate the effectiveness of our proposed model.

11 April 2025 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
GWGuoqing Wang
Guoqing Wang
WWWen Wu
Wen Wu
GYGuangze Ye
Guangze Ye
ZCZhenxiao Cheng
Zhenxiao Cheng
XCXi Chen
Xi Chen
HZHong Zheng
Hong Zheng
Large Language Models (LLMs) are known to hallucinate facts and make non-factual statements which can undermine trust in their output. The essence of hallucination lies in the absence of metacognition in LLMs, namely the understanding of their own cognitive processes. However, there has been limited research on quantitatively measuring metacognition within LLMs. Drawing inspiration from cognitive psychology theories, we first quantify the metacognitive ability of LLMs as their ability to evaluate the correctness of responses through confidence. Subsequently, we introduce a general framework called DMC designed to decouple metacognitive ability and cognitive ability. This framework tackles the challenge of noisy quantification caused by the coupling of metacognition and cognition in current research, such as calibration-based metrics. Specifically, the DMC framework comprises two key steps. Initially, the framework tasks the LLM with failure prediction, aiming to evaluate the model's performance in predicting failures, a performance jointly determined by both cognitive and metacognitive abilities of the LLM. Following this, the framework disentangles metacognitive ability and cognitive ability based on the failure prediction performance, providing a quantification of the LLM's metacognitive ability independent of cognitive influences. Experiments conducted on eight datasets across five domains reveal that (1) Our proposed DMC framework effectively separates the metacognition and cognition of LLMs; (2) Various confidence elicitation methods impact the quantification of metacognitve ability differently; (3) Stronger metacognitive ability are exhibited by LLMs with better overall performance; (4) Enhancing metacognition holds promise for alleviating hallucination issues.